DINO Re=1000
Previous-study tFNO-conditioned full-field EDM baseline for 2-D incompressible MHD decaying turbulence. The implementation and released tFNO conditioner are attributed to the MIT-licensed DINOs project by Semih Kacmaz.
- Channels: [ux, uy, A]
- Reynolds numbers: Re=Rm=1000
- Conditioner:
conditioner/model.safetensors - Diffusion model:
diffusion/model.safetensors - Normalization:
normalization/
Load
import torch
from phase import PHASEPipeline
model = PHASEPipeline.from_pretrained(
"phaseMHD/DINO-Re1000",
device="cuda" if torch.cuda.is_available() else "cpu",
)
# Physical initial condition: [batch, channels, x, y]
# The turbulence models were trained on 26 frames from t=0 to t=1.
times = torch.linspace(0.0, 1.0, 26, device=model.device)
prediction = model.predict(initial_fields, times, re=1000, seed=0)
# prediction: [batch, channels, time, x, y]
Install the runtime from PHASE:
pip install "phase[hub,dino,scot] @ git+https://github.com/PHASE-MHD/PHASE.git"
The package contains model-only weights, exact inference configs, and training-derived normalization statistics. See pipeline.yaml and provenance.json for the artifact mapping.